资源列表
设计模式14号
- 区域生长是一种很重要的图像分割方法。它是指从某个像素出发,比较相邻接像素的特征向量(包括灰度、边缘、纹理等特征),在预先指定的准则下,若它们足够相似则作为同一区域合并,以此方式使相似特征的区域不断增长,最后形成分割图像。(segmentation; cut apart; break up; excision; comminute)
opencv
- opencv图片先灰度化,然后自适应阈值把图片变为黑白双色(二值化)。输出纯黑白图片(opencv The image is grayscale first, and then the adaptive threshold turns the picture into black and white (two value). Output pure black and white pictures)
AntiVC_v2.6_sdk_Python
- 次世代V2.6版本的SDK实例,python。(The SDK instance of the V2.6 version of the second generation, python.)
histogram_matching_8bit
- 8bit 图像 自适应对比度增强——直方图匹配法以及直方图均衡法(8bit Histogram Matching)
KinectFusion
- 显示红外图,深度图,并获取KinectFusion模型(Display infrared maps, depth maps, and get KinectFusion models)
生物识别
- 基于win32和win64的生物识别学习资料(Biometric learning data based on Win32 and win64)
entropy_fuzzy_threshold
- 算法步骤: (1) 计算图像直方图,灰度级为Ns,图像的平均灰度值为Tc; (2) 分别计算第一个灰度级和其余灰度级的信息熵并求和,前两个灰度级和其余灰度级的信息熵并求和,以此类推计算Ns个和; (3) 找到H在Tc附近最大值的位置Tenf即为阈值; (4) 图像中大于阈值的像素置1,其余置0而实现二值分割。 算法的核心:信息熵越大越有不确定性,分割出的图片越好。(Algorithm steps: (1) the histogram of the image is calcula
python-dbn-master
- 运用python语言,基于dbn的手写数字体识别(Handwritten numeral recognition based on dbn using python language)
BF
- 能够很好地实现图像的去噪滤波,简单的人脸“磨皮”功能(The denoising filtering of the image can be realized well, and the simple face "wear skin" function)
chapter19
- 在MATLAB平台上的基于svm的手写数字体识别(Handwritten numeral recognition based on svm)
rddata
- 读取MIT-BIH ecg文件,将二进制数据转换为十进制,可绘制波形和读取备注信息。(read ecg data from the MIT-BIH database.)
qwt-6.1.3
- This is a classic qt painting third-party library, and its own qt provides the painting class library is not very complete, this source code can carry on meticulous painting.